A Two-Stage Parser for Multilingual Dependency Parsing

Proceedings of the CoNLL Shared Task Session of EMNLP-CoNLL 2007, pp. 1129–1133, Prague, June 2007. c⃝2007 Association for Computational Linguistics A Two-stage Parser for Multilingual Dependency Parsing Wenliang Chen, Yujie Zhang, Hitoshi Isahara Computational Linguistics Group National Institute of Information and Communications Technology 3-5 Hikari-dai, Seika-cho, Soraku-gun, Kyoto, Japan, 619-0289 {chenwl, yujie, isahara}@nict.go.jp Abstract We present a two-stage multilingual de- pendency parsing system submitted to the Multilingual Track of CoNLL-2007. The parser first identifies dependencies using a deterministic parsing method and then labels those dependencies as a sequence labeling problem. We describe the features used in each stage. For four languages with differ- ent values of ROOT, we design some spe- cial features for the ROOT labeler. Then we present evaluation results and error analyses focusing on Chinese. 1 Introduction The CoNLL-2007 shared tasks include two tracks: the Multilingual Track and Domain Adaptation Track(Nivre et al., 2007). We took part the Multi- lingual Track of all ten languages provided by the CoNLL-2007 shared task organizers(Hajiˇc et al., 2004; Aduriz et al., 2003; Mart´ı et al., 2007; Chen et al., 2003; B¨ohmov´a et al., 2003; Marcus et al., 1993; Johansson and Nugues, 2007; Prokopidis et al., 2005; Csendes et al., 2005; Montemagni et al., 2003; Oflazer et al., 2003) . In this paper, we describe a two-stage parsing system consisting of an unlabeled parser and a se- quence labeler, which was submitted to the Multi- lingual Track. At the first stage, we use the pars- ing model proposed by (Nivre, 2003) to assign the arcs between the words. Then we obtain a depen- dency parsing tree based on the arcs. At the sec- ond stage, we use a SVM-based approach(Kudo and Matsumoto, 2001) to tag the dependency label for each arc. The labeling is treated as a sequence la- beling problem. We design some special features for tagging the labels of ROOT for Arabic, Basque, Czech, and Greek, which have different labels for ROOT. The experimental results show that our ap- proach can provide higher scores than average. 2 Two-Stage Parsing 2.1 The Unlabeled Parser The unlabeled parser predicts unlabeled directed de- pendencies. This parser is primarily based on the parsing models described by (Nivre, 2003). The al- gorithm makes a dependency parsing tree in one left- to-right pass over the input, and uses a stack to store the processed tokens. The behaviors of the parser are defined by four elementary actions (where TOP is the token on top of the stack and NEXT is the next token in the original input string): • Left-Arc(LA): Add an arc from NEXT to TOP; pop the stack. • Right-Arc(RA): Add an arc from TOP to NEXT; push NEXT onto the stack. • Reduce(RE): Pop the stack. • Shift(SH): Push NEXT onto the stack. Although (Nivre et al., 2006) used the pseudo- projective approach to process non-projective de- pendencies, here we only derive projective depen- dency tree. We use MaltParser(Nivre et al., 2006) 1129 V0.41 to implement the unlabeled parser, and use the SVM …

Content truncated to 500 words